source: trunk/c++_tools/statistics/SAM.cc @ 675

// $Id: SAM.cc 675 2006-10-10 12:08:45Z jari $

/*
  Copyright (C) The authors contributing to this file.

  This file is part of the yat library, http://lev.thep.lu.se/trac/yat

  The yat library is free software; you can redistribute it and/or
  modify it under the terms of the GNU General Public License as
  published by the Free Software Foundation; either version 2 of the
  License, or (at your option) any later version.

  The yat library is distributed in the hope that it will be useful,
  but WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  General Public License for more details.

  You should have received a copy of the GNU General Public License
  along with this program; if not, write to the Free Software
  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  02111-1307, USA.
*/

#include "yat/statistics/SAM.h"
#include "yat/statistics/Averager.h"
#include "yat/statistics/AveragerWeighted.h"
#include "yat/classifier/DataLookupWeighted1D.h"
#include "yat/classifier/Target.h"
#include "yat/utility/vector.h"

#include <cmath>

namespace theplu {
namespace statistics {  

  SAM::SAM(const double s0, bool b) 
    : Score(b), s0_(s0)
  {
  }

  double SAM::score(const classifier::Target& target, 
                    const utility::vector& value)
  {
    weighted_=false;
    statistics::Averager positive;
    statistics::Averager negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value(i));
      else
        negative.add(value(i));
    }
    if(positive.n()+negative.n()<=2) 
      return 0;
    double diff = positive.mean() - negative.mean();
    double s2 = ( (1.0/positive.n()+1.0/negative.n()) * 
                 (positive.sum_xx_centered()+negative.sum_xx_centered()) /
                 (positive.n()+negative.n()-2) );
    if (diff<0 && absolute_)
      return -diff/(sqrt(s2)+s0_);
    return diff/(sqrt(s2)+s0_);
  }

  double SAM::score(const classifier::Target& target, 
                    const classifier::DataLookupWeighted1D& value)
  {
    weighted_=true;
    statistics::AveragerWeighted positive;
    statistics::AveragerWeighted negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value.data(i),value.weight(i));
      else
        negative.add(value.data(i),value.weight(i));
    }
    if(positive.n()+negative.n()<=2) 
      return 0;
    double diff = positive.mean() - negative.mean();
    double s2 = ( (1.0/positive.n()+1.0/negative.n()) * 
                 (positive.sum_xx_centered()+negative.sum_xx_centered()) /
                 (positive.n()+negative.n()-2) );
    if (diff<0 && absolute_)
      return -diff/(sqrt(s2)+s0_);
    return diff/(sqrt(s2)+s0_);
  }



  double SAM::score(const classifier::Target& target, 
                    const utility::vector& value,
                    const utility::vector& weight)
  {
    weighted_=true;
    statistics::AveragerWeighted positive;
    statistics::AveragerWeighted negative;
    for(size_t i=0; i<target.size(); i++){
      if (target.binary(i))
        positive.add(value(i),weight(i));
      else
        negative.add(value(i),weight(i));
    }
    if(positive.n()+negative.n()<=2) 
      return 0;
    double diff = positive.mean() - negative.mean();
    double s2 = ( (1.0/positive.n()+1.0/negative.n()) * 
                 (positive.sum_xx_centered()+negative.sum_xx_centered()) /
                 (positive.n()+negative.n()-2) );
    if (diff<0 && absolute_)
      return -diff/(sqrt(s2)+s0_);
    return diff/(sqrt(s2)+s0_);
  }



}} // of namespace statistics and namespace theplu